EconBase
← All papers

An Auditable AI Agent Loop for Empirical Economics: A Case Study in Forecast Combination

Minchul Shin

arXiv 18 Mar 2026 · Econometrics

arXiv:2603.17381 · PDF · DOI · OpenAlex · Extracted main text

Abstract

AI coding agents make empirical specification search fast and cheap, but they also widen hidden researcher degrees of freedom. Building on an open-source agent-loop architecture, this paper adapts that framework to an empirical economics workflow and adds a post-search holdout evaluation. In a forecast-combination illustration, multiple independent agent runs outperform standard benchmarks in the original rolling evaluation, but not all continue to do so on a post-search holdout. Logged search and holdout evaluation together make adaptive specification search more transparent and help distinguish robust improvements from sample-specific discoveries.

Citation extraction

14
references
31
in-text mentions
14
distinct cited
2
self-citations
2,584
main-text words

appendix boundary found by appendix_command · 29% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Diebold, Francis X. and Shin, Minchul (2019) Machine Learning for Regularized Survey Forecast Combination: Partially-Egalitarian LASSO and Its Derivatives self0.87412767%
2Karpathy, Andrej (2026) autoresearch0.6444250%
3Novikov, Alexander and Vũ, Ngân and Eisenberger, Marvin and Dupont,… (2025) AlphaEvolve: A coding agent for scientific and algorithmic discovery0.64422100%
4Shin, Minchul and Schor, Nathan (2026) ForeComp: An R Package for Comparing Predictive Accuracy Using Fixed-Smoothing Asymptotics self0.5113233%
5Aygün, Eser and Belyaeva, Anastasiya and Comanici, Gheorghe and Cora… (2025) An AI System to Help Scientists Write Expert-Level Empirical Software0.40511100%
6Nam, Jaehyun and Yoon, Jinsung and Chen, Jiefeng and Sinha, Raj and… (2025) DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries0.40511100%
7Dawid, Herbert and Harting, Philipp and Wang, Hankui and Wang, Zhong… (2025) Agentic Workflows for Economic Research: Design and Implementation0.40511100%
8Gelman, Andrew and Loken, Eric (2013) The Garden of Forking Paths: Why Multiple Comparisons Can Be a Problem, Even When There Is No “Fishing Expedition” or “p-Hacking…0.40511100%
9Gottweis, Juraj and Weng, Wei-Hung and Daryin, Alexander and Tu, Tao… (2025) Towards an AI co-scientist0.40511100%
10Korinek, Anton (2025) AI Agents for Economic Research0.40511100%

Showing the top 10 of 14 scored citations.